Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59350
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terminology and detailed descriptions of complex systems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @xiaoqingsun004
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    霸王
    -0.07
     dictated
    -0.07
    .Debugf
    -0.07
    完
    -0.06
    刑
    -0.06
    🐡
    -0.06
     timeouts
    -0.06
     exert
    -0.06
     PartialView
    -0.06
     gross
    -0.06
    POSITIVE LOGITS
    ユーザ
    0.08
    hta
    0.08
     kole
    0.07
    (Label
    0.07
    .environment
    0.07
     scr
    0.07
     şimdi
    0.06
    sembling
    0.06
    Sense
    0.06
    Separator
    0.06
    Activations Density 0.845%

    No Known Activations